Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Only readOnlyHint is provided, so the description carries the behavioral burden and does so richly: it states the comparison 'never ranks' and invents no score, that credits left is reduced 'only by items a school's own rules cover' and never by an unknown or inferred item, that payback is withheld and the missing input named when either input is unpublished, and that GoldCheck states/reasons are carried through unchanged. That is substantial disclosure beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening hook is front-loaded, and nearly every clause carries a real rule (no ranking, credit reduction limits, payback guard, state passthrough) rather than filler. It is dense, em-dash-heavy, and reads as one long paragraph, which costs some readability, but little of the content is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need not be described, and the description still covers comparison scope, input-conditional behavior, and the key non-ranking constraint. The only material gap is explicit routing guidance against the other compare_ siblings, which the rich schema and annotations do not supply.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The prose adds conceptual meaning for the optional 'held' input (what each school's published rules would count courses/exams for) and reinforces the 2-5 school bound, but 'package' and 'level' get no added semantics beyond the schema, so the description only marginally exceeds the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('Which of these schools is better for me?') and pins the scope tightly: 'Two to five schools, one major and a level, side by side.' It also enumerates the compared dimensions (program, credits, requirements, cost, earnings, debt, payback), which sharpens what 'compare' means. It stops short of naming sibling tools such as compare_my_major or compare_destinations, so differentiation is implied rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the framing ('Two to five schools, one major and a level') and by the conditional 'when the person offers their courses and exam scores,' which quietly describes an optional input path. There is no explicit when-to-use versus when-not, and no named alternative among the four sibling 'compare_' tools, so the agent must infer routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.